stanza

stanza copied to clipboard

Can't get a binary tree using stanza.pipeline

12

**Describe the bug** Can't get a binary tree using stanza.pipeline

ZhichaoDuan

POS tagging's unexpected result on ADJ word

11

**Describe the bug** For this sentence, ``` He also designed furniture and houses for the wealthy. ``` `wealthy` is a adjective that exceptionally head a nominal phrase, which should be...

muchang

To implement SOTA text summarization architecture

3

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is to have a module that provides text summarization. This is...

techverve

Stanza does not work when parallel processing rows in data frame

3

I have a dataframe with 800,000 rows and for each row, I want to find the person mentioned in each comment (row.comment). I want to use Stanza because it has...

esidoda

Bias not used

3

Hi, it seems this bias weight in `PairwiseBilinear` is not used. Possibly a (minor) bug? https://github.com/stanfordnlp/stanza/blob/1c73418b65905b2d32f7b0dcb0bdd4a615b6ab0a/stanza/models/common/biaffine.py#L17

kmkurn

Where is Semantic Dependency Parsing?

2

I am looking for the code for Semantic Dependency Parsing. https://github.com/tdozat/Parser-v3 said I should be able to find it in the https://github.com/stanfordnlp/stanfordnlp/ repo. But that repo is marked obsolete, replaced...

xoffey

Arabic words being changed from the original text in the lemmatization process

9

If you see the commands below, for any single word identified, the lemma is being shown as different which for me is a bug. Please, correct me if not and...

hugomelo

NER model training for Armenian

2

**Is your feature request related to a problem? Please describe.** I'm testing a trained NER model for Armenian for my project. After obtaining tangible results of its performance, this might...

Hovhannisian

Edge case dependency tree causes parser to fail

5

**Describe the bug** During the parsing of [this wiki page](https://en.wikipedia.org/wiki?curid=52074018), the parser fails with the following traceback: ``` Traceback (most recent call last): File "", line 1, in File "/path/pyenv/versions/3.10.2/lib/python3.10/site-packages/stanza/pipeline/core.py",...

taiqihe

Currently the depparse training uses gold lemmas. This means that at runtime, the lemmas the parser sees for user text or ETE scoring are slightly different. 4% in the case...

AngledLuffa